Papers › ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

30 Jul 2018ECCV 2018 9arXiv:1807.11164archive 2025-07-28

Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun

Datasets, Transforms and Models specific to Computer Vision

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1807.11164")

Code

Syntology Ran 1 of 30 code samples harvested from 8 repositories linked to this paper; 29 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 30 samples from 8 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

35 repositories listed; official and paper-mentioned ones first.

CellProfiling/HPA-Special-Prize mentioned on GitHubtfApache-2.0 report
PaulGitt/ShuffleNetV2-tensorflow mentioned on GitHubtfApache-2.0 report
Qengineering/ShuffleNetV2-ncnn mentioned on GitHubBSD-3-Clause report
Yang-YiFan/DiracDeltaNet mentioned on GitHubpytorch report
allenai/dnw mentioned on GitHubpytorch report
ba-san/MobilePose-Pi mentioned on GitHubpytorch report
deep-learning-algorithm/LightWeightCNN mentioned on GitHubpytorch report
emilianavt/OpenSeeFace mentioned on GitHubtfBSD-2-Clause report
lyqcom/shufflenetv2 mentioned on GitHubmindsporeApache-2.0 report
mnicnc404/CartoonGan-tensorflow mentioned on GitHubtfApache-2.0 report
opconty/keras-shufflenetV2 mentioned on GitHub report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
savageyusuff/MobilePose-Pi mentioned on GitHubpytorch report
sokeeffe/caffe_yolo mentioned on GitHubNOASSERTION report
tensorpack/tensorpack mentioned on GitHubtf report
zjZSTU/LightWeightCNN mentioned on GitHubpytorchApache-2.0 report
MegEngine/Models NOASSERTION report
PaddlePaddle/PaddleClas paddleApache-2.0 report
open-mmlab/mmpose pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

30 samples harvested; 1 ran; 0 honoured the contract we drafted; 29 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
29unverified

Licence: 0 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 8 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

channel_shuffle zjZSTU/LightWeightCNN/py/lib/models/shufflenet_v2/inverted_residual.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b9da06d4f527dd6c · report
DiracDeltaNet_wrapper Yang-YiFan/DiracDeltaNet/models/diracdeltanet.py community (archive-listed) unverified Apache-2.0 (permissive) · 6b203d6dc2a5b668 · report
ShuffleNetv2_wrapper Yang-YiFan/DiracDeltaNet/models/shufflenetv2.py community (archive-listed) unverified Apache-2.0 (permissive) · 445ec0988e64e403 · report
accuracy megvii-model/ShuffleNet-Series/ShuffleNetV1/utils.py community (archive-listed) unverified MIT (permissive) · 469bf48752905889 · report
calcul_acc lyqcom/shufflenetv2/postprocess.py community (archive-listed) unverified Apache-2.0 (permissive) · 5af3c724a0f8260c · report
central_crop tropcomplique/shufflenet-v2-tensorflow/input_pipeline.py community (archive-listed) unverified MIT (permissive) · a2dd1b47b92453bf · report
channel_shuffle megvii-model/ShuffleNet-Series/ShuffleNetV2+/blocks.py community (archive-listed) unverified MIT (permissive) · eaa44944ca357418 · report
channel_shuffle PaulGitt/ShuffleNetV2-tensorflow/ShuffleNetV2Layer.py community (archive-listed) unverified Apache-2.0 (permissive) · 1f2313e2d5c77242 · report
channel_shuffle_2 mnicnc404/CartoonGan-tensorflow/layers.py community (archive-listed) unverified Apache-2.0 (permissive) · 047d2adb2aa60175 · report
concat_shuffle_split tropcomplique/shufflenet-v2-tensorflow/architecture.py community (archive-listed) unverified MIT (permissive) · f3c9a6ea00c7a858 · report
conv_layer mnicnc404/CartoonGan-tensorflow/style_transfer/cartoongan/cartoongan.py community (archive-listed) unverified Apache-2.0 (permissive) · b7aa9d638640fd66 · report
deconv_layers mnicnc404/CartoonGan-tensorflow/style_transfer/cartoongan/cartoongan.py community (archive-listed) unverified Apache-2.0 (permissive) · ca657d934bcd2edf · report
get_logger mnicnc404/CartoonGan-tensorflow/logger.py community (archive-listed) unverified Apache-2.0 (permissive) · f68f4a5d6df2ac7f · report
get_padding mnicnc404/CartoonGan-tensorflow/layers.py community (archive-listed) unverified Apache-2.0 (permissive) · 2fa780cf05243f82 · report
get_parameters megvii-model/ShuffleNet-Series/ShuffleNetV1/utils.py community (archive-listed) unverified MIT (permissive) · 9a700a3b149f4952 · report
get_random_crop tropcomplique/shufflenet-v2-tensorflow/input_pipeline.py community (archive-listed) unverified MIT (permissive) · d21f11381e618e69 · report
instance_norm_layer mnicnc404/CartoonGan-tensorflow/style_transfer/cartoongan/cartoongan.py community (archive-listed) unverified Apache-2.0 (permissive) · 286a52cbf168ada5 · report
load_test_data CellProfiling/HPA-Special-Prize/inference/special_eval.py community (archive-listed) unverified Apache-2.0 (permissive) · e5b4c800ffeec6c5 · report
post_processing mnicnc404/CartoonGan-tensorflow/cartoonize.py community (archive-listed) unverified Apache-2.0 (permissive) · b1dee98f6e19456f · report
pre_process_image CellProfiling/HPA-Special-Prize/inference/predict.py community (archive-listed) unverified Apache-2.0 (permissive) · ac24f40859e3a94f · report
pre_processing mnicnc404/CartoonGan-tensorflow/cartoonize.py community (archive-listed) unverified Apache-2.0 (permissive) · ef3323039d6f13b6 · report
read_fov_images CellProfiling/HPA-Special-Prize/inference/special_eval.py community (archive-listed) unverified Apache-2.0 (permissive) · d4aa0c5d57122c3f · report
resize_keeping_aspect_ratio tropcomplique/shufflenet-v2-tensorflow/input_pipeline.py community (archive-listed) unverified MIT (permissive) · a6ea3219aaef3a26 · report
save_transformed_image mnicnc404/CartoonGan-tensorflow/cartoonize.py community (archive-listed) unverified Apache-2.0 (permissive) · 7fa659f5c52cd503 · report
shufflenet_g_1 zjZSTU/LightWeightCNN/py/lib/models/shufflenet/shufflenet.py community (archive-listed) unverified Apache-2.0 (permissive) · 73b69322397c17cd · report
shufflenet_g_2 zjZSTU/LightWeightCNN/py/lib/models/shufflenet/shufflenet.py community (archive-listed) unverified Apache-2.0 (permissive) · ccf9120247e232c4 · report
shufflenet_g_3 zjZSTU/LightWeightCNN/py/lib/models/shufflenet/shufflenet.py community (archive-listed) unverified Apache-2.0 (permissive) · 128ca4f685f83b5a · report
shufflenetv2block PaulGitt/ShuffleNetV2-tensorflow/ShuffleNetV2Layer.py community (archive-listed) unverified Apache-2.0 (permissive) · 7d6072fb5e206973 · report
shufflenetv2block_withsubsample PaulGitt/ShuffleNetV2-tensorflow/ShuffleNetV2Layer.py community (archive-listed) unverified Apache-2.0 (permissive) · e50ce69643b1c686 · report
topk_accuracy zjZSTU/LightWeightCNN/py/lib/utils/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 10e6a9dbdece7f97 · report

Tasks

Image ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ShuffleNet V2 GFLOPs 0.597 #948 of 1060 Archive leaderboard report
Image Classification ImageNet ShuffleNet V2 Top 1 Accuracy 75.4% #948 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: ShuffleNet V2 Block, ShuffleNet V2 Downsampling Block

1x1 ConvolutionAverage PoolingBatch NormalizationChannel ShuffleConvolutionDense ConnectionsDepthwise ConvolutionGlobal Average PoolingReLUResidual ConnectionShuffleNet V2 BlockShuffleNet V2 Downsampling BlockShuffleNet v2Sigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStep DecayWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections